Gen Agent Trust Hub

renewal-radar · anthropics/knowledge-work-plugins

Passed

Provider summary

This skill is designed with several security considerations in mind. It includes explicit instructions for handling untrusted content from emails and chats, preventing indirect prompt injection by treating such data as information rather than instructions. It also mandates human review for actions originating from untrusted content and employs secure linking practices. The skill is authored by a trusted vendor, and its behaviors are consistent with its stated purpose.

The provider classified the analyzed snapshot as NONE risk. This result applies to the content available at audit time.

Interpretation

Compare the repository, publisher, and installation command before continuing.

Review SKILL.md, scripts, and allowed tools. OpenAI Suite never executes them during indexing.

Use the narrowest possible scope and avoid broad credentials for third-party skills.